Answers are grounded in this paper and cite their sources.
A family of surrogate spatial interaction models is developed and tested. The family consists of eight separate but related models: four classes with two models per class. The surrogate models differ from conventional models with respect to structure, numbers of parameters, and computational complexity. The first section of the paper draws the distinction between conventional and surrogate spatial interaction models. The second section presents the family of surrogate models being considered. The third section of the paper is devoted to an empirical test of the models in analyzing data from three spatial systems: an outdoor recreation system, a university enrollment system, and a professional society system. Issues relevant to selecting the most appropriate class of model are discussed.
No takes yet. Share an insight, caveat, or question.
Frank J. Cesario (1976) studied this question.
Synapse has enriched 5 related papers. Consider them for comparative context: